© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 63473
    Prev
    Next
    INDEX
    Explanations

    locations and contexts related to energy or power sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CompatActivity
    -0.17
    //{{
    -0.15
    uate
    -0.15
    onas
    -0.14
    ellers
    -0.14
    jte
    -0.14
    eli
    -0.14
    theid
    -0.14
    омеÑĢ
    -0.14
    arro
    -0.14
    POSITIVE LOGITS
     charg
    0.17
    ink
    0.17
    avier
    0.16
     acid
    0.15
    lements
    0.15
    sea
    0.15
    asta
    0.15
    roy
    0.15
    lags
    0.15
    -oper
    0.15
    Activations Density 0.003%

    No Known Activations